Documentation

1. Create an account

2. Create an API key

3. Start making requests

Python

from openai import OpenAI

client = OpenAI(
    base_url="https://api.orbit.hyfysoft.com/v1",
    api_key="sk_orbit_live_..."
)

# Access any Chinese LLM through OpenAI SDK
response = client.chat.completions.create(
    model="deepseek-v3.2",  # or qwen-max, glm-5, kimi-k2.5, ...
    messages=[{"role": "user", "content": "Hello"}]
)

TypeScript

import OpenAI from "openai";

const client = new OpenAI({
  baseURL: "https://api.orbit.hyfysoft.com/v1",
  apiKey: "sk_orbit_live_...",
});

const response = await client.chat.completions.create({
  model: "deepseek-v3.2",
  messages: [{ role: "user", content: "Hello" }],
});

cURL

curl https://api.orbit.hyfysoft.com/v1/chat/completions \
  -H "Authorization: Bearer sk_orbit_live_..." \
  -H "Content-Type: application/json" \
  -d '{
    "model": "deepseek-v3.2",
    "messages": [{"role": "user", "content": "Hello"}]
  }'

Endpoint

POST /v1/messages

Python (Anthropic SDK)

import anthropic

client = anthropic.Anthropic(
    base_url="https://api.orbit.hyfysoft.com/v1",
    api_key="sk_orbit_live_..."
)

message = client.messages.create(
    model="qwen3.5-plus",
    max_tokens=1024,
    messages=[
        {"role": "user", "content": "Hello, how are you?"}
    ]
)
print(message.content[0].text)

cURL

curl https://api.orbit.hyfysoft.com/v1/messages \
  -H "x-api-key: sk_orbit_live_..." \
  -H "anthropic-version: 2023-06-01" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "qwen3.5-plus",
    "max_tokens": 1024,
    "messages": [{"role": "user", "content": "Hello"}]
  }'

Authentication

Both x-api-key and Authorization: Bearer headers are supported. Use your Orbit API key for either method.

Endpoint

POST /v1/images/generations

Python (OpenAI SDK)

from openai import OpenAI

client = OpenAI(
    base_url="https://api.orbit.hyfysoft.com/v1",
    api_key="sk_orbit_live_..."
)

response = client.images.generate(
    model="wanx",  # or cogview-4, minimax-image, step-image
    prompt="A serene mountain landscape at sunset",
    n=1,
    size="1024x1024"
)
print(response.data[0].url)

Available Image Models

Endpoints

POST /v1/videos/generations    # Submit generation task
GET  /v1/videos/{task_id}      # Query task status

Python

import requests
import time

# Submit video generation task
response = requests.post(
    "https://api.orbit.hyfysoft.com/v1/videos/generations",
    headers={"Authorization": "Bearer sk_orbit_live_..."},
    json={
        "model": "cogvideox",  # or seedance-2, minimax-video
        "prompt": "A cat playing piano in a cozy room",
        "duration": 5,
        "resolution": "1080p"
    }
)
task = response.json()
task_id = task["id"]
print(f"Task submitted: {task_id}")

# Poll for completion
while True:
    status = requests.get(
        f"https://api.orbit.hyfysoft.com/v1/videos/{task_id}",
        headers={"Authorization": "Bearer sk_orbit_live_..."}
    ).json()
    if status["status"] == "completed":
        print(f"Video URL: {status['url']}")
        break
    time.sleep(5)

Available Video Models

Endpoint

POST /v1/audio/speech

Python

import requests

response = requests.post(
    "https://api.orbit.hyfysoft.com/v1/audio/speech",
    headers={"Authorization": "Bearer sk_orbit_live_..."},
    json={
        "model": "cosyvoice-v2",  # or minimax-speech, step-tts
        "input": "Hello, welcome to Orbit.",
        "voice": "alloy"
    }
)
with open("speech.mp3", "wb") as f:
    f.write(response.content)

cURL

curl https://api.orbit.hyfysoft.com/v1/audio/speech \
  -H "Authorization: Bearer sk_orbit_live_..." \
  -H "Content-Type: application/json" \
  -d '{
    "model": "cosyvoice-v2",
    "input": "Hello, welcome to Orbit.",
    "voice": "alloy"
  }' \
  --output speech.mp3

Available Audio Models

Text Models (LLM)

Available Models →